Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.5027. Min Act: -0.1700
Data Index: 2391990 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.4402. Min Act: -0.1700
Data Index: 244204 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.4089. Min Act: -0.1700
Data Index: 535755 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.3464. Min Act: -0.1700
Data Index: 4973849 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.2214. Min Act: -0.1700
Data Index: 1432305 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.2527. Min Act: -0.1700
Data Index: 1846606 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.2527. Min Act: -0.1700
Data Index: 7867938 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.2214. Min Act: -0.1700
Data Index: 7780529 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.2214. Min Act: -0.1700
Data Index: 1335313 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.2214. Min Act: -0.1700
Data Index: 916111 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.2527. Min Act: -0.1700
Data Index: 8482811 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.2214. Min Act: -0.1700
Data Index: 6986984 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.1902. Min Act: -0.1700
Data Index: 8409707 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.1902. Min Act: -0.1700
Data Index: 3457456 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.1902. Min Act: -0.1700
Data Index: 8807383 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.1589. Min Act: -0.1700
Data Index: 2670991 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.1589. Min Act: -0.1700
Data Index: 8283337 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.1589. Min Act: -0.1700
Data Index: 8199289 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.1589. Min Act: -0.1700
Data Index: 554881 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5027. Min Range: -6.5027
Max Act: 6.1589. Min Act: -0.1700
Data Index: 2360965 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19